α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Bettina Messmer
Bettina Messmer
4
papers
101
total citations
papers (4)
FineWeb2: One Pipeline to Scale Them All — Adapting Pre-Training Data Processing to Every Language
COLM 2025
arXiv
51
citations
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks
ICML 2024
arXiv
33
citations
Enhancing Multilingual LLM Pretraining with Model-Based Data Selection
NEURIPS 2025
arXiv
12
citations
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
ICML 2025
arXiv
5
citations